EP1333682A1 - Bewegungsdetektion von einem kodierten Bilddatenstrom - Google Patents

Bewegungsdetektion von einem kodierten Bilddatenstrom Download PDF

Info

Publication number
EP1333682A1
EP1333682A1 EP20030250540 EP03250540A EP1333682A1 EP 1333682 A1 EP1333682 A1 EP 1333682A1 EP 20030250540 EP20030250540 EP 20030250540 EP 03250540 A EP03250540 A EP 03250540A EP 1333682 A1 EP1333682 A1 EP 1333682A1
Authority
EP
European Patent Office
Prior art keywords
motion
image
detecting
bit stream
image data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
EP20030250540
Other languages
English (en)
French (fr)
Inventor
Jae-soo 812-2004 Byukjeokgol 8danji Hansin Cho
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hanwha Techwin Co Ltd
Original Assignee
Samsung Electronics Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Samsung Electronics Co Ltd filed Critical Samsung Electronics Co Ltd
Publication of EP1333682A1 publication Critical patent/EP1333682A1/de
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/238—Interfacing the downstream path of the transmission network, e.g. adapting the transmission rate of a video stream to network bandwidth; Processing of multiplex streams
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
    • H04N19/51—Motion estimation or motion compensation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
    • H04N19/157—Assigned coding mode, i.e. the coding mode being predefined or preselected to be further used for selection of another element or parameter
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
    • H04N19/157—Assigned coding mode, i.e. the coding mode being predefined or preselected to be further used for selection of another element or parameter
    • H04N19/159—Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
    • H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
    • H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/48—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using compressed domain processing techniques other than decoding, e.g. modification of transform coefficients, variable length coding [VLC] data or run-length data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal prediction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/80—Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/90—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using coding techniques not provided for in groups H04N19/10-H04N19/85, e.g. fractals

Definitions

  • the present invention relates to a video motion detection method and a video motion detection apparatus.
  • Motion detection i.e. Detection of movement within the scene captured by a camera, is used to trigger the sending of an image to a remote operator for viewing on a PDA or an IMT terminal or uploading of the image to an FTP server.
  • the monitoring system can be effectively operated without unnecessarily loading the system because of the large amount of data. Furthermore, when only images captured when there is movement in the scene are stored into a hard disk, as in the case of a DVR (Digital Video Recorder) for example, the efficiency of the hard disk usage can be improved. Thus, when a DVR product or a network monitoring system has a motion detection function, the efficiency of the product is improved.
  • DVR Digital Video Recorder
  • a conventional method of motion detection is based on the difference between successive image. More particularly, a statistical value, such as an average or a standard deviation, is derived from the pixel values is a difference image, i.e. the result of subtracting the pixels of one image from another, is compared with an empirically determined threshold so that the motion can be detected from the image.
  • a statistical value such as an average or a standard deviation
  • Figure 1 is a block diagram of a conventional apparatus for detecting motion in an input image using the difference image technique
  • Figure 2 is a flowchart showing a method of detecting motion used by the detecting apparatus shown in Figure 1.
  • a conventional motion detecting apparatus comprises an A/D conversion unit 10, a filtering unit 20, a memory 30, an operation unit 40, a comparison unit 50 and a warning unit 60.
  • the A/D conversion unit 10 initially converts an analogue image signal, from a camera, into a digital signal. Noise is removed from the converted digital image data at the noise removing filtering unit 20, and then the noise-free converted digital image data is input into the memory 30 and the operation unit 40.
  • the memory 30 stores a previously input image (P) and a currently input image (C) for comparison and, at operation 30, the operation unit 40 obtains a difference image (D) from the noise free currently input image (C) and the previously input image (P), stored in the memory 30.
  • the comparison unit 50 compares the difference image (D) value for each pixel with a threshold (t1) to determine which pixels are in a moving part of the scene and, at operations 41, 42, a motion binarization process generates a binarized motion image by setting each pixel to one one of two values, corresponding to motion and static, in operation 40). Then, at operation 50, the operation unit 40 calculates the sum ( ⁇ BD) of the pixels of the binarized image (BD). At operation 60, the sum ( ⁇ BD) of the pixels of the binarized image (BD) is compared with a predetermined threshold (t2). At operation 60, if the sum ( ⁇ BD) of the binarized image (BD) is greater than the threshold (t2), it is determined that there has been motion scene and, at operation 70, a motion detection warning is generated by the warning unit 60.
  • the motion detecting method using the difference image can obtain a great amount of information from each pixel unit and has the advantage of detecting motion by using various statistical features of the difference image.
  • the operation of the conventional motion detection method is slow because data is obtained and processed for each pixel and there is a disadvantage in that the detected result can be sensitive to or negatively impacted by camera noise or a change in the external environment.
  • the method of detecting the motion in an input image by using the difference image requires extra frame memory to store the previous and current input image data to compare the previously input image and the currently input image.
  • Such a method also requires a noise-removing filter to prevent mis-operation caused by the camera noise.
  • a video motion detection method is characterised by obtaining inter-frame coded frames of a video bit stream comprising inter-frame and intra-frame coded frames, maintaining an average of the inter-frame coded frame bit lengths and determining the presence of motion in the scene represented by said video bitstream using said average.
  • a video motion detection apparatus is characterised by means for obtaining inter-frame coded frames of a video bit stream comprising inter-frame and intra-frame coded frames, means for maintaining an average of the inter-frame coded frame bit lengths and means for determining the presence of motion in the scene represented by said video bitstream using said average.
  • the presence of motion may be detected by comparing said average with a threshold.
  • the presence of motion is preferably detected by comparing the rate of change of said average with a threshold.
  • the means for extracting inter-frame coded frames, the means for maintaining an average of the inter-frame coded frame bit length and the means for determining the presence of motion in the scene represented by said video bitstream using said average may be implemented by a programmed computer.
  • a signal e.g. a series data packets, representing computer program codes for programming a computer to form an apparatus according to the present invention.
  • the signal may be an electric or electromagnetic signal.
  • a data carrier e.g. a CDROM, from which a signal according to the present invention can be reproduced.
  • an image processing system comprises an image input unit 100, an A/D conversion unit 110, an image compression unit 120, a separation unit 130, an operation unit 140, a comparison unit 150, an output unit 160 and a transmission unit 170.
  • the image input unit 100 is a device, such as a video camera, for converting an image into an electrical signal.
  • the image signal may be analogue or digital depending on the nature of the image input unit 100. If the image signal is analogue, the A/D conversion unit 110 converts it into a digital signal.
  • the image compression unit 120 encodes and compresses the digital image signal received from the A/D conversion unit 110 (or the image input unit 100 if it is a digital device). There are two kinds of frames in the bit stream output by the image compression unit 120. In the first kind, the bit stream is formed by encoding the received digital image signal with motion predicton. In the second kind, the bit stream is formed by encoding the the received digital image signal without motion prediction.
  • the motion prediction can use an inter mode (i.e. based upon an inter-frame compression technique) that transmits the difference between first and second frames in terms of motion vectors for macro blocks.
  • an intra mode compression technique such Discrete Cosine Transform (DCT) is applied to the current frame without reference the neighbouring frames.
  • DCT Discrete Cosine Transform
  • the separation unit 130 separates out the frames for which the inter mode encoding and compression has been used by the image compression unit 120. In other words, the the inter mode coded frames, but not the intra mode coded frames, in the bit stream are passed to the operation unit 140.
  • the operation unit 140 calculates an average value of the inter mode frames from the separation unit 130.
  • the comparison unit 150 compares a signal corresponding to the average value input from the operation unit 140 with a signal corresponding to a threshold set up in advance, and if the signal corresponding to the average value is greater than the threshold, the comparison unit 150 determines that there is motion in the scene and sends a detection signal to the output unit 160.
  • the output unit 160 determines that there is movement (motion) when the detection signal is transmitted from the comparison unit 150 to the output unit 160, and outputs a warning signal in response to the detected motion. For example, a warning sound can be generated or a warning message can be transmitted to a remote terminal, such as a wireless terminal.
  • the transmission unit 170 transmits the frame in which motion was detected through a network in response to a warning signal (e.g., when a warning signal is transmitted from the output unit 160 to the transmission unit 170, etc.).
  • the output unit 160 and the transmission unit 170 can be part of an existing network image monitoring system and interfaced with processing units 110 through 150.
  • the average value of the inter mode coded frames can be a substantially reliable predictor of motion. More particularly, an increase in the average value of the inter mode coded frames indicates motion and, thus, when detected enables a motion detection signal to be reliably output.
  • the processes of the present invention as embodied in units 100 through 150 can be implemented using software and/or hardware as part of a main processing unit of a network digital image monitoring system receiving video camera signals (e.g., a computer server).
  • the main processing unit would output and/or transmit information (e.g. warning signals, images, etc.) to other devices of the network digital image monitoring system, in response to detected motion in images received from a camera monitoring an area.
  • the A/D conversion unit 110 converts the analogue signal into a digital signal.
  • the digital signal is input into the image compression unit 120 and encoded according to an encoding method to output compressed bit streams.
  • the image compression unit 120 uses a combination of inter-frame and intra-frame compression/encoding methods, as in MPEG (Moving Picture Experts Group) encoding, which encodes the received digital image signal.
  • MPEG Motion Picture Experts Group
  • the separation unit 130 separates the inter mode coded frames (i.e. B- and P- frames) from the intra mode coded frames by passing only the inter mode coded frames to the operation unit 440.
  • the operation unit 140 obtains an average size value (Ma) for the data representing the inter-mode coded frames.
  • the average value of the inter mode coded frames is very small when there is little movement but increases when there is movement.
  • the comparison unit 150 compares the average value with a set up threshold T 1, at operation 450.
  • a corresponding motion signal indicating motion detection, is output. More particularly, at operation 450, if it is determined that the average value for the inter mode coded frames is greater than the threshold T 1 , at operation 460, the output unit 160 determines there is motion in the received image sequence in response to the motion detection signal from the comparison unit 150 and outputs a warning signal in response to the motion detection.
  • the transmission unit 170 can transmit the image data with the detected motion through the network based on the warning signal.
  • the output unit 160 implemented as a control process (software) can control warning of motion detection, storing of corresponding image data, or transmission of a motion detection message by electronic messaging, e.g. Email or SMS, to a PDA or a mobile phone.
  • electronic messaging e.g. Email or SMS
  • the operation unit 140 obtains the average value (Ma) of the inter mode image bit stream, and after that, at operation 441, calculates the change (DMa) of the average value (Ma) between successive frames.
  • the comparison unit 150 determines whether there is movement in the received image signal by comparing the obtained change (DMa) with a threshold T 2 . More particularly, at operation 442, if the obtained change is greater than the threshold T 2 , the comparison unit 150 determines that there is motion in the received image signal and outputs a motion detection signal to the output unit 160.
  • the change in the average between the inter mode coded frames is almost zero when there is little movement. Yet, when there is movement in the received image signal, the change in the average (DMa) between inter mode coded frames is very large compared to the case that there is not movement.
  • the threshold T 2 is set according empirically.
  • the output unit 160 determines that there is motion in the received image signal in dependence on the motion detection signal from the comparison unit 150 and outputs a warning signal in response to the motion detection. More particularly, the processes of operation 445 by the output unit 160 are similar to the processes of the output unit 160 at operation 460 in Figure 5A.
  • the image input unit 100 can be one or more video cameras installed in to monitor an monitored area and in communication, via a network, with a main processing unit (not shown), such as a computer. Typically, the processes of the present invention are implemented in the processing unit. Typically, the image input unit 100 transmits image data as an analogue signal to the processing unit when a camera is an analogue camera and the image input unit 100 transmits the image data as a digital signal when the camera is a digital camera. When the image data is input as an analog signal, the image data is converted into a digital signal by the A/D conversion unit 110. When the image input unit 100 comprises digital video cameras, the A/D conversion unit 110 does not have to be installed (i.e. the A/D conversion unit 110 may be omitted).
  • the automatic monitoring system network can, for example, transmit the image signal to other components and devices, such as a display monitor, and can compress the input image signal for storage in a DVR.
  • the image compression unit 120 encodes the image signal, using a combination of inter-frame and intra-frame compression techniques.
  • the image compression unit 120 outputs an encoded bit stream.
  • the bit stream output from the image compression unit 120 is transmitted to the separation unit 130.
  • the separation unit 130 is set up to pass the inter mode coded frames only.
  • the operation unit 140 calculates the average value of the amount data required for an inter mode coded frame and transmits a signal corresponding to the average value to the comparison unit 150.
  • the comparison unit 150 compares the input average value signal with a predetermined threshold. When the average value is greater than the threshold, it is determined that there is movement in the received image signal and a corresponding motion signal is output. If the average value is less than the threshold, it is determined that there is no movement.
  • the average data size is very large.
  • a threshold can be easily determined and a motion in a frame image can be easily detected based upon size of the average value of the inter mode coded frames.
  • detection of a motion is improved.
  • the corresponding motion signal is output from the comparison unit 150, it has been determined that there is movement in the received image signal and the signal is transmitted to the output unit 160 from the comparison unit 150.
  • the output unit 160 can output a warning signal, in response to the received motion signal from the comparison unit 150.
  • the warning signal is output, the frame with the detected motion is stored into the DVR and variously emails or other message types are sent to an owner, the police or a security company.
  • the emails or oither messages may included the frame with the motion and use sound.
  • frames 1, 6 and 11 are intra mode coded frames (I-Frame)
  • frames 3, 4, 5, 7, 8, 9, 10 and 12 are inter mode coded frames (B-Frames and P-Frames)
  • the solid line is the average bit length.
  • a motion is included in frame 3.
  • the bit length of the intra mode coded frames are more than the average bit length.
  • bit length of the inter mode coded frames when there is little motion in the image, the bit length of the inter mode coded frames is almost zero, see for example frame 2.
  • bit length of the inter mode coded frames when there is much motion in the image, the bit length of the inter mode coded frames is long in relation to the average bit length for inter mode bit coded frames,see for example frames 7, 8, 9, 10 and 12. Therefore, motion can be easily and reliably detected if the bit length of an inter mode coded frame is longer than the average bit length of the inter mode coded frames.
  • the average bit length value for the whole encoded bit stream i.e. with both inter mode and intra mode coded frames, shows very little change in response to motion occuring. Even, if a threshold is set high, the motion is hardly detectable. Thus, supporting the rationale for excluding the intra mode image bit stream.
  • Figures 7B and 8B when only the inter mode coded frames are used, the deviation arising from motion is great in relation to the average bit length of the inter mode coded frames and, thus, motion is easily and reliably detected even though a low threshold has been set.
  • the apparatus detecting motion in image signals and the method thereof according the present invention can easily and reliably detect motion by using inter mode coded frames after removing intra mode coded frames from the bit streams of the image.
  • the motion of the image can be detected by using an encoded bit stream already generated by compression processes in an image monitoring system, for example, for purpose of recording/archiving, without adding a separate circuitry or memory. More particularly, typically, only software processes utilizing the generated encoded bit streams are implemented in the image monitoring system. Further, motion detection can be more reliable by substantially reducing false motion detections because of an image signal noise.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Image Analysis (AREA)
EP20030250540 2002-02-05 2003-01-29 Bewegungsdetektion von einem kodierten Bilddatenstrom Ceased EP1333682A1 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2002-0006572A KR100465244B1 (ko) 2002-02-05 2002-02-05 영상 데이터의 움직임 감지장치 및 방법
KR2002006572 2002-02-05

Publications (1)

Publication Number Publication Date
EP1333682A1 true EP1333682A1 (de) 2003-08-06

Family

ID=19719121

Family Applications (1)

Application Number Title Priority Date Filing Date
EP20030250540 Ceased EP1333682A1 (de) 2002-02-05 2003-01-29 Bewegungsdetektion von einem kodierten Bilddatenstrom

Country Status (5)

Country Link
US (1) US7280596B2 (de)
EP (1) EP1333682A1 (de)
JP (1) JP2003288599A (de)
KR (1) KR100465244B1 (de)
CN (1) CN1189031C (de)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7868912B2 (en) 2000-10-24 2011-01-11 Objectvideo, Inc. Video surveillance system employing video primitives
US7932923B2 (en) 2000-10-24 2011-04-26 Objectvideo, Inc. Video surveillance system employing video primitives
US8564661B2 (en) 2000-10-24 2013-10-22 Objectvideo, Inc. Video analytic rule detection system and method
US8711217B2 (en) 2000-10-24 2014-04-29 Objectvideo, Inc. Video surveillance system employing video primitives
EP2770740A1 (de) * 2013-02-20 2014-08-27 Honeywell International Inc. System und Verfahren zur Bewegungsdetektion in komprimiertem Video
US9892606B2 (en) 2001-11-15 2018-02-13 Avigilon Fortress Corporation Video surveillance system employing video primitives
CN113194357A (zh) * 2021-01-25 2021-07-30 妙微(杭州)科技有限公司 一种运动目标检测方法及系统

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100620950B1 (ko) 2004-09-14 2006-09-19 주식회사 애트랩 광 마우스 및 이 장치의 제어 방법
JP4698260B2 (ja) * 2005-03-25 2011-06-08 三洋電機株式会社 画像記録装置及び監視システム
US7366356B2 (en) * 2005-08-05 2008-04-29 Seiko Epson Corporation Graphics controller providing a motion monitoring mode and a capture mode
CN100417223C (zh) * 2005-12-30 2008-09-03 浙江工业大学 基于全方位视觉传感器的智能安保装置
KR100837406B1 (ko) * 2006-11-13 2008-06-12 삼성전자주식회사 영상 감시 장치를 포함한 휴대 단말기 및 이를 이용한 영상감시 방법, 및 영상 감시 시스템
JP5244625B2 (ja) * 2009-01-19 2013-07-24 株式会社日立国際電気 画像圧縮伸張装置
US8625005B2 (en) * 2010-11-05 2014-01-07 Raytheon Company First-in-first-out (FIFO) buffered median scene non-uniformity correction method
US9369668B2 (en) * 2014-03-14 2016-06-14 Cisco Technology, Inc. Elementary video bitstream analysis
KR101592731B1 (ko) 2014-07-09 2016-02-05 주식회사 에스원 영상 감시 시스템
US20160161339A1 (en) * 2014-12-05 2016-06-09 Intel Corporation Human motion detection

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1021042A1 (de) * 1999-01-14 2000-07-19 Mitsubishi Denki Kabushiki Kaisha Verfahren zur Szenenänderungs- und Überblendungensdetektion für Videosequenzindexierung
EP1065877A1 (de) * 1999-07-01 2001-01-03 Mitsubishi Denki Kabushiki Kaisha Segmentidentifizierung für komprimierte Bilddatenströme

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6313863B1 (en) * 1994-07-29 2001-11-06 Canon Kabushiki Kaisha Image communication apparatus and system
JPH1023393A (ja) 1996-06-28 1998-01-23 U S C:Kk 動体検出方法
JP3223962B2 (ja) * 1997-01-24 2001-10-29 松下電器産業株式会社 画像復号化方法
JP2000209570A (ja) 1999-01-20 2000-07-28 Toshiba Corp 移動物体監視装置
US6618507B1 (en) * 1999-01-25 2003-09-09 Mitsubishi Electric Research Laboratories, Inc Methods of feature extraction of video sequences

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1021042A1 (de) * 1999-01-14 2000-07-19 Mitsubishi Denki Kabushiki Kaisha Verfahren zur Szenenänderungs- und Überblendungensdetektion für Videosequenzindexierung
EP1065877A1 (de) * 1999-07-01 2001-01-03 Mitsubishi Denki Kabushiki Kaisha Segmentidentifizierung für komprimierte Bilddatenströme

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JIAN FENG ET AL: "Scene change detection algorithm for MPEG video sequence", PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) LAUSANNE, SEPT. 16 - 19, 1996, NEW YORK, IEEE, US, vol. 1, 16 September 1996 (1996-09-16), pages 821 - 824, XP010202784, ISBN: 0-7803-3259-8 *
JONES B J T: "Low-cost outdoor video motion and non-motion detection", SECURITY TECHNOLOGY, 1995. PROCEEDINGS. INSTITUTE OF ELECTRICAL AND ELECTRONICS ENGINEERS 29TH ANNUAL 1995 INTERNATIONAL CARNAHAN CONFERENCE ON SANDERSTEAD, UK 18-20 OCT. 1995, NEW YORK, NY, USA,IEEE, US, 18 October 1995 (1995-10-18), pages 376 - 381, XP010196440, ISBN: 0-7803-2627-X *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9378632B2 (en) 2000-10-24 2016-06-28 Avigilon Fortress Corporation Video surveillance system employing video primitives
US10026285B2 (en) 2000-10-24 2018-07-17 Avigilon Fortress Corporation Video surveillance system employing video primitives
US8564661B2 (en) 2000-10-24 2013-10-22 Objectvideo, Inc. Video analytic rule detection system and method
US8711217B2 (en) 2000-10-24 2014-04-29 Objectvideo, Inc. Video surveillance system employing video primitives
US10645350B2 (en) 2000-10-24 2020-05-05 Avigilon Fortress Corporation Video analytic rule detection system and method
US10347101B2 (en) 2000-10-24 2019-07-09 Avigilon Fortress Corporation Video surveillance system employing video primitives
US7932923B2 (en) 2000-10-24 2011-04-26 Objectvideo, Inc. Video surveillance system employing video primitives
US7868912B2 (en) 2000-10-24 2011-01-11 Objectvideo, Inc. Video surveillance system employing video primitives
US9892606B2 (en) 2001-11-15 2018-02-13 Avigilon Fortress Corporation Video surveillance system employing video primitives
US10321132B2 (en) 2013-02-20 2019-06-11 Honeywell International Inc. System and method for detecting motion in compressed video
US9497479B2 (en) 2013-02-20 2016-11-15 Honeywell International Inc. System and method for detecting motion in compressed video
US9053366B2 (en) 2013-02-20 2015-06-09 Honeywell International Inc. System and method for detecting motion in compressed video
EP2770740A1 (de) * 2013-02-20 2014-08-27 Honeywell International Inc. System und Verfahren zur Bewegungsdetektion in komprimiertem Video
CN113194357A (zh) * 2021-01-25 2021-07-30 妙微(杭州)科技有限公司 一种运动目标检测方法及系统

Also Published As

Publication number Publication date
US20030151062A1 (en) 2003-08-14
CN1437412A (zh) 2003-08-20
US7280596B2 (en) 2007-10-09
KR100465244B1 (ko) 2005-01-13
KR20030066234A (ko) 2003-08-09
JP2003288599A (ja) 2003-10-10
CN1189031C (zh) 2005-02-09

Similar Documents

Publication Publication Date Title
EP1333682A1 (de) Bewegungsdetektion von einem kodierten Bilddatenstrom
US7933333B2 (en) Method and apparatus for detecting motion in MPEG video streams
US9756348B2 (en) Method, device and system for producing a merged digital video sequence
US9424747B2 (en) Vehicle counting methods and systems utilizing compressed video streams
US20030112866A1 (en) Method and apparatus for motion detection from compressed video sequence
EP3402204A1 (de) Codierung eines videostroms mit privatsphärenmaske
JP4456867B2 (ja) ビデオ中の異常イベントを検出する方法およびシステム
EP2770740B1 (de) Verfahren und Vorrichting zur Bewegungsdetektion in komprimiertem Video
KR102215627B1 (ko) 비디오 스트림을 인코딩하기 위한 방법, 비디오 인코더, 및 비디오 카메라
Costanzo et al. Detection of double AVC/HEVC encoding
US20040189792A1 (en) Security system using mobile phone
CN111277800A (zh) 监控视频编码及播放方法、装置、电子设备及存储介质
JPH07231442A (ja) 防犯監視装置
WO2022057746A1 (zh) 一种图像处理方法、装置、设备及计算机可读存储介质
JP4157661B2 (ja) 動画像内の移動物体検出方法および装置
KR20220048935A (ko) 비디오 이미지의 시퀀스를 인코딩하기 위한 이미지 프로세싱 장치, 카메라 및 방법
JP5244625B2 (ja) 画像圧縮伸張装置
JP3886784B2 (ja) 動画像内の物体識別装置及び方法
JP2003111061A (ja) 動体検出装置、動体検出システムおよび動体検出方法
JP3658016B2 (ja) ディジタル画像の通信・記録装置、送信装置、受信装置
JP3085003U (ja) 動体検出装置および動体検出システム
JP3435746B2 (ja) 遠隔監視装置
US20240163456A1 (en) Method and a device for managing encoded image frames in a data buffer
JP3523471B2 (ja) 遠隔画像監視システム
Heath et al. Segmentation of MPEG-2 motion imagery within the compressed domain

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PT SE SI SK TR

AX Request for extension of the european patent

Extension state: AL LT LV MK RO

17P Request for examination filed

Effective date: 20030913

AKX Designation fees paid

Designated state(s): DE FR GB IT

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SAMSUNG ELECTRONICS CO., LTD.

17Q First examination report despatched

Effective date: 20040827

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SAMSUNG TECHWIN CO., LTD

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION HAS BEEN REFUSED

18R Application refused

Effective date: 20110614